Objectives that hold. Records you can trust. Models you can swap.
The engine is where the difficult, general work lives. It assembles context before a conversation starts, holds working memory during it, enforces conversation policy turn by turn, executes the objective ladder, mediates every tool call, and produces a structured record at the end. It is channel agnostic and language agnostic by construction, so the same worker logic drives a phone call, a message thread and a web chat in any supported language.
Most conversational agents are given a goal. Hub workers are given an ordered, procedural sequence in which each rung is a materially different outcome, and a lower rung may only be attempted once the higher one is genuinely closed off.
Intelligence captured opportunistically where the conversation allows, never worked as a checklist and never at the cost of the ladder. They are the difference between a booking service and an intelligence asset.
A narrative summary cannot be reported on, compared, or scored. A structured contract can. This is the object every downstream system reads from.
| Field group | What it holds |
|---|---|
| Outcome | A required level from a closed set matching the ladder, a one line summary of what was agreed, and a status distinguishing confirmed, where a day and time were explicit, from tentative |
| Upgrade & confirmation | A higher outcome partially in play but not confirmed, and how and when anything tentative will be confirmed, as agreed with the contact |
| Disposition | Sentiment toward your company, and readiness to engage further |
| Commercial intelligence | Initiatives with funding stage and timing, the principal pain, who else shares the concern, competitive presence and contract timing, new leaders and newly created roles |
| Relationship | Referrals with the level secured, being a name, permission to reference, or a promised introduction; channel permissions and stated preferences; every organisation and person mentioned with a clause of context |
| Corrections | Which of our prior assumptions were confirmed or corrected, with the corrected fact |
| Suppression | Any explicit request for no further contact, recorded in the contact's own terms with its scope |
Fields are populated only from evidence in the conversation, and anything unknown is omitted rather than invented. A record built on inference would be worthless the moment anyone relied on it.
A single concatenated prompt cannot be safely edited by a customer, cannot be improved centrally without touching every deployment, and cannot tell you which change caused a regression. Layers solve all three.
The invariant core: the priority stack, honesty and disclosure rules, the settled topic ledger, turn discipline, ladder mechanics, tool and contract semantics, the ending protocol. Corvair engineering only.
Personality, register, voice binding, gendered language handling, conversational style defaults. Selected by you from the template library.
The domain: inside sales, property, collections. Vocabulary, outcome level names, intelligence field labels, domain guardrails.
Company identity, brand voice, product and pricing boundaries, escalation contacts, jurisdictional posture. Edited by your administrator, within limits the kernel enforces.
The engagement briefing and its objective ladder, authored by your sales operations team.
Contact, account intelligence, memory, prior interaction notes, language and channel state. Assembled by the runtime and never hand edited.
Conversational latency and analytical depth are opposing requirements, and they should never be served by one configuration. Each worker carries an engine profile binding a model class to each task class it performs.
| Task class | Requirement | Typical binding |
|---|---|---|
| Live conversation | Sub second first token, streaming audio, interruption handling. Depth traded for latency | A low latency live model |
| In conversation retrieval | Fast, grounded, cited. Runs inside a turn without stalling it | A fast model against the substrate |
| Post conversation analysis | Rigorous, evidence bound, schema conformant. Latency irrelevant | A deliberative reasoning model |
| Coaching and revision | The highest reasoning demand in the system. Must produce surgical, defensible edits | A deliberative model, elevated thinking |
| Research and briefing | Long running, tool using, grounded in search | A deliberative model with search grounding |
| Extraction and enrichment | High volume, structured, cheap | A small fast model |
Google is the first voice provider and ElevenLabs is the named alternate. Two implementations rather than one is what makes the interface real rather than aspirational, because an interface with a single implementation behind it is a guess.
A live turn wants minimal deliberation. An evaluator scoring a transcript wants a great deal. Fixing one value platform wide either makes conversations sluggish or makes analysis shallow.
Sixteen languages today, with detection and following provided as a runtime service rather than as agent logic.
Detect and continue in their language, including mid conversation switches, with correct gendered grammar and politeness where the language requires it.
The live transcript is never translated or rewritten. It is the evidentiary record of what was actually said.
A parallel rendering in your record language, so structured fields, notes and CRM evidence stay consistent regardless of what was spoken.
The language a contact is served in, the language records are kept in, and the language your team reads dashboards in are three separate settings.
When a conversation moves from a message thread to a voice call, the context travels with the contact, so the worker on the call knows exactly what was discussed in text ten minutes earlier.
The current thread, the contact's recent statements, the live objective rung, the settled topic ledger and the next step options.
Recent conversation summaries, pending actions, referral chains in progress, qualification captured, and the state of each active flow.
Relationship history, stakeholder profiles, initiative signals, competitive intelligence. Institutional memory that survives personnel change.
A canonical, attributed chronology of decisions, actions and pivots, from which working context is derived rather than stored, so continuity stays explainable.
Everything that varies by customer, channel or system sits behind an adapter. That is what lets one runtime serve a seller, a collections specialist and a property assistant without a fork.